Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 12 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0115. Min Range: -5.0115

Max Act: 5.0115. Min Act: -0.1699

Data Index: 1557532 (Python Code)

Max Activating Token Index: 216

Text #1

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.8708. Min Act: -0.1699

Data Index: 1408454 (Python Code)

Max Activating Token Index: 598

Text #2

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.8318. Min Act: -0.1699

Data Index: 1655481 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.7087. Min Act: -0.1699

Data Index: 1445188 (Python Code)

Max Activating Token Index: 342

Text #4

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.6814. Min Act: -0.1699

Data Index: 1532697 (Python Code)

Max Activating Token Index: 735

Text #5

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.5974. Min Act: -0.1699

Data Index: 1422874 (Python Code)

Max Activating Token Index: 989

Text #6

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.6462. Min Act: -0.1699

Data Index: 1389715 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.5612. Min Act: -0.1699

Data Index: 1450722 (Python Code)

Max Activating Token Index: 709

Text #8

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.5241. Min Act: -0.1699

Data Index: 1637757 (Python Code)

Max Activating Token Index: 628

Text #9

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.6130. Min Act: -0.1699

Data Index: 1636304 (Python Code)

Max Activating Token Index: 644

Text #10

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.5241. Min Act: -0.1699

Data Index: 1449896 (Python Code)

Max Activating Token Index: 869

Text #11

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.5075. Min Act: -0.1699

Data Index: 1538120 (Python Code)

Max Activating Token Index: 909

Text #12

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.5427. Min Act: -0.1699

Data Index: 1534546 (Python Code)

Max Activating Token Index: 832

Text #13

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.5134. Min Act: -0.1699

Data Index: 1473607 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.5329. Min Act: -0.1699

Data Index: 1500760 (Python Code)

Max Activating Token Index: 214

Text #15

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.5046. Min Act: -0.1699

Data Index: 1522502 (Python Code)

Max Activating Token Index: 465

Text #16

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.4851. Min Act: -0.1699

Data Index: 1458879 (Python Code)

Max Activating Token Index: 480

Text #17

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.4607. Min Act: -0.1699

Data Index: 1588700 (Python Code)

Max Activating Token Index: 460

Text #18

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.4607. Min Act: -0.1699

Data Index: 1368214 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 5.0115. Min Range: -5.0115

Max Act: 4.4138. Min Act: -0.1699

Data Index: 1378133 (Python Code)

Max Activating Token Index: 874